In this paper, we introduce the task of style-consistent content transfer, which concerns modifying a text’s content based on a provided reference statement while preserving its original style. We approach the task by employing multi-task learning to ensure that the modified text meets three important conditions: reference faithfulness, style adherence, and coherence. In particular, we train three independent classifiers for each condition. During inference, these classifiers are used to determine the best modified text variant. Our evaluation, conducted on hotel reviews and news articles, compares our approach with sequence-to-sequence and error correction baselines. The results demonstrate that our approach reasonably generates text satisfying all three conditions. In subsequent analyses, we highlight the strengths and limitations of our approach, providing valuable insights for future research directions.
Wei-Fan Chen, Milad Alshomary, Maja Stahl, Khalid Al Khatib, Benno Stein, and Henning Wachsmuth. 2024.Reference-guided Style-Consistent Content Transfer. InProceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13754–13768, Torino, Italia. ELRA and ICCL.
@inproceedings{chen-etal-2024-reference, title = "Reference-guided Style-Consistent Content Transfer", author = "Chen, Wei-Fan and Alshomary, Milad and Stahl, Maja and Al Khatib, Khalid and Stein, Benno and Wachsmuth, Henning", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.1201/", pages = "13754--13768", abstract = "In this paper, we introduce the task of style-consistent content transfer, which concerns modifying a text`s content based on a provided reference statement while preserving its original style. We approach the task by employing multi-task learning to ensure that the modified text meets three important conditions: reference faithfulness, style adherence, and coherence. In particular, we train three independent classifiers for each condition. During inference, these classifiers are used to determine the best modified text variant. Our evaluation, conducted on hotel reviews and news articles, compares our approach with sequence-to-sequence and error correction baselines. The results demonstrate that our approach reasonably generates text satisfying all three conditions. In subsequent analyses, we highlight the strengths and limitations of our approach, providing valuable insights for future research directions."}
%0 Conference Proceedings%T Reference-guided Style-Consistent Content Transfer%A Chen, Wei-Fan%A Alshomary, Milad%A Stahl, Maja%A Al Khatib, Khalid%A Stein, Benno%A Wachsmuth, Henning%Y Calzolari, Nicoletta%Y Kan, Min-Yen%Y Hoste, Veronique%Y Lenci, Alessandro%Y Sakti, Sakriani%Y Xue, Nianwen%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)%D 2024%8 May%I ELRA and ICCL%C Torino, Italia%F chen-etal-2024-reference%X In this paper, we introduce the task of style-consistent content transfer, which concerns modifying a text‘s content based on a provided reference statement while preserving its original style. We approach the task by employing multi-task learning to ensure that the modified text meets three important conditions: reference faithfulness, style adherence, and coherence. In particular, we train three independent classifiers for each condition. During inference, these classifiers are used to determine the best modified text variant. Our evaluation, conducted on hotel reviews and news articles, compares our approach with sequence-to-sequence and error correction baselines. The results demonstrate that our approach reasonably generates text satisfying all three conditions. In subsequent analyses, we highlight the strengths and limitations of our approach, providing valuable insights for future research directions.%U https://aclanthology.org/2024.lrec-main.1201/%P 13754-13768
Wei-Fan Chen, Milad Alshomary, Maja Stahl, Khalid Al Khatib, Benno Stein, and Henning Wachsmuth. 2024.Reference-guided Style-Consistent Content Transfer. InProceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13754–13768, Torino, Italia. ELRA and ICCL.